arXiv Statistics ML October 26, 2026 By Qin Li, Maria Oprea, Li Wang, Yunan Yang

Stochastic Inverse Problem: stability, regularization and Wasserstein gradient flow

Read the original on arXiv Statistics ML →

The paper investigates stochastic inverse problems where the goal is to recover a probability distribution of an unknown parameter that explains observed data. It examines direct inversion, a variational formulation with regularization, and optimization via Wasserstein gradient flows, highlighting parallels and differences with deterministic inverse problems. A key finding is that the choice of metric—both in the loss function and during optimization—strongly influences stability and the optimizer’s properties.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Statistics ML.

arXiv Machine Learning

Jun 30

Learning from samples: inverse problems over measures

arXiv:2505. 07124v3 Announce Type: replace Abstract: We study inverse problems where an unknown potential is observed only through samples from the measure it induces by a convex variational principle.

By Francisco Andrade, Gabriel Peyr\'e, Clarice Poon

arXiv Machine Learning

Sep 17

A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Models

arXiv:2509.19276v2 Announce Type: replace-cross Abstract: Solving ill-posed inverse problems requires powerful and flexible priors. We propose leveraging pretrained latent diffusion models for this t...

By Tim Y. J. Wang, O. Deniz Akyildiz

diffusion benchmarks

arXiv Machine Learning

Jul 10

Statistical inverse learning problems with random observations

arXiv:2312. 15341v1 Announce Type: cross Abstract: We provide an overview of recent progress in statistical inverse problems with random experimental design, covering both linear and nonlinear inverse problems.

By Abhishake Rastogi, Tapio Helin, Nicole M\"ucke

arXiv Machine Learning

Aug 3

P-Flow: Proxy-gradient Flows for Linear Inverse Problems

arXiv:2605. 08328v3 Announce Type: replace Abstract: Generative models based on flow matching have emerged as a powerful paradigm for inverse problems, offering straighter trajectories and faster sampling compared to diffusion models.

By Zehua Jiang, Fenghao Zhu, Xinquan Wang, Chongwen Huang, Zhaoyang Zhang

diffusion

arXiv Machine Learning

Sep 15

Stochastic Gradient Descent over P2

The paper develops a diffusion approximation for stochastic gradient descent (SGD) when the optimization target is a functional on the Wasserstein space ℝ2. By lifting the problem to a Hilbert space via Lions differentiability, the authors construct a Gaussian random-field approximation whose velocity field matches the mean and covariance of the original stochastic gradient. They prove that this Gaussian approximation achieves second‑order weak accuracy, providing a rigorous basis for replacing sample‑driven randomness with analytically tractable Gaussian fluctuations in stochastic optimization over probability measures.

By Maria Oprea, Qin Li, Yunan Yang

diffusion

arXiv Machine Learning

Jun 30

A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems

arXiv:2606. 30230v1 Announce Type: cross Abstract: Learned reconstruction operators for inverse problems are typically trained under a fixed noise model, and generalize poorly when the distribution during testing differs from the one assumed during training.

By Floor van Maarschalkerwaart, Subhadip Mukherjee, Christoph Brune, Marcello Carioni

safety

One email a morning, machine-written

Related stories

Learning from samples: inverse problems over measures

A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Models

Statistical inverse learning problems with random observations

P-Flow: Proxy-gradient Flows for Linear Inverse Problems

Stochastic Gradient Descent over P2

A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems